陈意辉的第四次作业

 1 from datetime import datetime
 2 from datetime import timedelta
 3 from datetime import *
 4 start_day = datetime(2019, 4, 1)
 5 end_day = datetime(2019, 4, 30)
 6 a=end_day-start_day
 7 amount = a.days + 1
 8 first=start_day.isoweekday()
 9 k = 1
10 count=0
11 print("\t\t\t2019年4月")
12 print("星期一\t星期二\t星期三\t星期四\t星期五\t星期六\t星期日")
13 while k < first:  
14     k=k+1
15     print("\t", end="")
16 p = 1
17 while p <= amount:  
18     print(p, "\t", end="")
19     p =p+1
20     count =count+1
21     if (count % 7 == 0):
22         print("\n")  

 1 import jieba
 2 excludes = {"一个","一回","袭人","银子","王夫人","东西","姑娘","什么"
 3             ,"我们","贾母","那里","说道","众人","一面","这个","不知","没有","两个"
 4             ,"奶奶","怎么","只见","自己","他们","出来","这里","起来","知道","如今","你们",
 5             "一个","我们","那里","如今","说道","知道","起来","姑娘","这里","出来",
 6             "他们","众人","自己","一面","只见","太太","两个","没有","不是","不知",
 7             "这个","听见","这样","进来","咱们","告诉","怎么","就是","东西","回来","只是",
 8             "老爷","大家","只得","丫头","这些","不敢","出去","所以","的话","不好","姐姐"}
 9 txt = open(r"C:\Users\ASUS\PycharmProjects\untitled\红楼梦.txt", "r", encoding='utf-8').read()
10 words  = jieba.lcut(txt)#精确模式的分词函数，返回一个列表数据类型
11 #print(type(words)) #words的数据类型
12 counts = {}  #定义一个字典
13 for word in words:
14     if len(word) == 1:
15         continue
16     elif word == "宝玉" or word == "宝二爷" or word == "怡红公子" or word == "绛洞花主" or word == "无事忙" or word == "遮天大王" or word == "混世魔王" or word == "槛内人" or word == "浊玉":
17         rword = "贾宝玉"
18     elif word == "林黛玉" or word == "黛玉道":
19         rword = "林黛玉"
20     elif word == "宝钗" or word == "蘅芜君" or word == "宝姐姐" or word == "宝丫头" or word == "宝姑娘":
21         rword = "薛宝钗"
22     elif word == "凤姐" or word == "琏二奶奶" or word=="凤辣子"or word=="凤哥儿"or word=="凤丫头" or word=="凤姐儿" or word == "熙凤道":
23         rword = "王熙凤"
24     elif word == "贾母" or word == "老太太":
25         rword = "贾母"
26     elif word == "贾探春" or word == "探春":
27         rword = "探春"
28     elif word == "秦可卿" or word == "可卿":
29         rword = "可卿"
30     elif word == "司棋" or word == "司棋道":
31         rword = "司棋"
32     else:
33         rword = word
34     counts[rword] = counts.get(rword,0) + 1 #词汇加入字典
35 for word in excludes:
36     del(counts[word])  #从字典中删除无用词
37 items = list(counts.items())#字典转换为列表
38 
39 #lambda是一个隐函数，是固定写法，以下命令的意思就是按照记录的第2列排序
40 """x表示列表中的一个元素，x只是临时起的一个名字，
41 你可以使用任意的名字"""
42 items.sort(key=lambda x:x[1], reverse=True)
43 
44 for i in range(7): #出现的词频统计
45     word, count = items[i] #将键和值分别赋予列表word和countf
46     print ("{0:<10}{1:>5}".format(word, count))#0:<10左对齐，宽度10，”>5"右对齐